© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 34187
    Prev
    Next
    INDEX
    Explanations

    ( at your option

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    /or
    -0.20
     then
    -0.08
    rei
    -0.08
     thus
    -0.08
     either
    -0.08
     Kak
    -0.08
    oulos
    -0.07
     Coch
    -0.07
    inh
    -0.07
    ares
    -0.07
    POSITIVE LOGITS
     alternatively
    0.24
    èĢħ
    0.23
     equival
    0.20
    ients
    0.20
    phans
    0.19
     simply
    0.18
    lando
    0.18
     worse
    0.17
    leans
    0.17
     else
    0.17
    Activations Density 0.184%

    No Known Activations